Optical Flow Algorithms

Classes
class	cv::optflow::DualTVL1OpticalFlow
	"Dual TV L1" Optical Flow Algorithm. More...
class	cv::optflow::GPCDetails
class	cv::optflow::GPCForest< T >
struct	cv::optflow::GPCMatchingParams
	Class encapsulating matching parameters. More...
struct	cv::optflow::GPCPatchDescriptor
struct	cv::optflow::GPCPatchSample
struct	cv::optflow::GPCTrainingParams
	Class encapsulating training parameters. More...
class	cv::optflow::GPCTrainingSamples
	Class encapsulating training samples. More...
class	cv::optflow::GPCTree
	Class for individual tree. More...
class	cv::optflow::OpticalFlowPCAFlow
	PCAFlow algorithm. More...
class	cv::optflow::PCAPrior
	This class can be used for imposing a learned prior on the resulting optical flow. Solution will be regularized according to this prior. You need to generate appropriate prior file with "learn_prior.py" script beforehand. More...

Typedefs
typedef std::vector< GPCPatchSample >	cv::optflow::GPCSamplesVector

Enumerations
enum	cv::optflow::GPCDescType {   cv::optflow::GPC_DESCRIPTOR_DCT = 0,   cv::optflow::GPC_DESCRIPTOR_WHT }
	Descriptor types for the Global Patch Collider. More...

Functions
double	cv::motempl::calcGlobalOrientation (InputArray orientation, InputArray mask, InputArray mhi, double timestamp, double duration)
	Calculates a global motion orientation in a selected region. More...
void	cv::motempl::calcMotionGradient (InputArray mhi, OutputArray mask, OutputArray orientation, double delta1, double delta2, int apertureSize=3)
	Calculates a gradient orientation of a motion history image. More...
void	cv::optflow::calcOpticalFlowSF (InputArray from, InputArray to, OutputArray flow, int layers, int averaging_block_size, int max_flow)
void	cv::optflow::calcOpticalFlowSF (InputArray from, InputArray to, OutputArray flow, int layers, int averaging_block_size, int max_flow, double sigma_dist, double sigma_color, int postprocess_window, double sigma_dist_fix, double sigma_color_fix, double occ_thr, int upscale_averaging_radius, double upscale_sigma_dist, double upscale_sigma_color, double speed_up_thr)
	Calculate an optical flow using "SimpleFlow" algorithm. More...
void	cv::optflow::calcOpticalFlowSparseToDense (InputArray from, InputArray to, OutputArray flow, int grid_step=8, int k=128, float sigma=0.05f, bool use_post_proc=true, float fgs_lambda=500.0f, float fgs_sigma=1.5f)
	Fast dense optical flow based on PyrLK sparse matches interpolation. More...
Ptr< DenseOpticalFlow >	cv::optflow::createOptFlow_DeepFlow ()
	DeepFlow optical flow algorithm implementation. More...
Ptr< DualTVL1OpticalFlow >	cv::optflow::createOptFlow_DualTVL1 ()
	Creates instance of cv::DenseOpticalFlow. More...
Ptr< DenseOpticalFlow >	cv::optflow::createOptFlow_Farneback ()
	Additional interface to the Farneback's algorithm - calcOpticalFlowFarneback() More...
Ptr< DenseOpticalFlow >	cv::optflow::createOptFlow_PCAFlow ()
	Creates an instance of PCAFlow. More...
Ptr< DenseOpticalFlow >	cv::optflow::createOptFlow_SimpleFlow ()
	Additional interface to the SimpleFlow algorithm - calcOpticalFlowSF() More...
Ptr< DenseOpticalFlow >	cv::optflow::createOptFlow_SparseToDense ()
	Additional interface to the SparseToDenseFlow algorithm - calcOpticalFlowSparseToDense() More...
void	cv::optflow::GPCForest< T >::findCorrespondences (InputArray imgFrom, InputArray imgTo, std::vector< std::pair< Point2i, Point2i > > &corr, const GPCMatchingParams params=GPCMatchingParams()) const
	Find correspondences between two images. More...
void	cv::motempl::segmentMotion (InputArray mhi, OutputArray segmask, std::vector< Rect > &boundingRects, double timestamp, double segThresh)
	Splits a motion history image into a few parts corresponding to separate independent motions (for example, left hand, right hand). More...
void	cv::motempl::updateMotionHistory (InputArray silhouette, InputOutputArray mhi, double timestamp, double duration)
	Updates the motion history image by a moving silhouette. More...

Detailed Description

Dense optical flow algorithms compute motion for each point:

• cv::optflow::calcOpticalFlowSF
• cv::optflow::createOptFlow_DeepFlow

Motion templates is alternative technique for detecting motion and computing its direction. See samples/motempl.py.

• cv::motempl::updateMotionHistory
• cv::motempl::calcMotionGradient
• cv::motempl::calcGlobalOrientation
• cv::motempl::segmentMotion

Functions reading and writing .flo files in "Middlebury" format, see: http://vision.middlebury.edu/flow/code/flow-code/README.txt

• cv::optflow::readOpticalFlow
• cv::optflow::writeOpticalFlow

Typedef Documentation

GPCSamplesVector

typedef std::vector< GPCPatchSample > cv::optflow::GPCSamplesVector

Enumeration Type Documentation

GPCDescType

enum cv::optflow::GPCDescType

Descriptor types for the Global Patch Collider.

Enumerator
GPC_DESCRIPTOR_DCT  Python: cv.optflow.GPC_DESCRIPTOR_DCT	Better quality but slow.
GPC_DESCRIPTOR_WHT  Python: cv.optflow.GPC_DESCRIPTOR_WHT	Worse quality but much faster.

Function Documentation

calcGlobalOrientation()

double cv::motempl::calcGlobalOrientation	(	InputArray	orientation,
		InputArray	mask,
		InputArray	mhi,
		double	timestamp,
		double	duration
	)

Python:
	retval	=	cv.motempl.calcGlobalOrientation(	orientation, mask, mhi, timestamp, duration	)

Calculates a global motion orientation in a selected region.

Parameters

orientation	Motion gradient orientation image calculated by the function calcMotionGradient
mask	Mask image. It may be a conjunction of a valid gradient mask, also calculated by calcMotionGradient , and the mask of a region whose direction needs to be calculated.
mhi	Motion history image calculated by updateMotionHistory .
timestamp	Timestamp passed to updateMotionHistory .
duration	Maximum duration of a motion track in milliseconds, passed to updateMotionHistory

The function calculates an average motion direction in the selected region and returns the angle between 0 degrees and 360 degrees. The average direction is computed from the weighted orientation histogram, where a recent motion has a larger weight and the motion occurred in the past has a smaller weight, as recorded in mhi .

calcMotionGradient()

void cv::motempl::calcMotionGradient	(	InputArray	mhi,
		OutputArray	mask,
		OutputArray	orientation,
		double	delta1,
		double	delta2,
		int	apertureSize = 3
	)

Python:
	mask, orientation	=	cv.motempl.calcMotionGradient(	mhi, delta1, delta2[, mask[, orientation[, apertureSize]]]	)

Calculates a gradient orientation of a motion history image.

Parameters

mhi	Motion history single-channel floating-point image.
mask	Output mask image that has the type CV_8UC1 and the same size as mhi . Its non-zero elements mark pixels where the motion gradient data is correct.
orientation	Output motion gradient orientation image that has the same type and the same size as mhi . Each pixel of the image is a motion orientation, from 0 to 360 degrees.
delta1	Minimal (or maximal) allowed difference between mhi values within a pixel neighborhood.
delta2	Maximal (or minimal) allowed difference between mhi values within a pixel neighborhood. That is, the function finds the minimum ( \(m(x,y)\) ) and maximum ( \(M(x,y)\) ) mhi values over \(3 \times 3\) neighborhood of each pixel and marks the motion orientation at \((x, y)\) as valid only if \[\min ( \texttt{delta1} , \texttt{delta2} ) \le M(x,y)-m(x,y) \le \max ( \texttt{delta1} , \texttt{delta2} ).\]
apertureSize	Aperture size of the Sobel operator.

The function calculates a gradient orientation at each pixel \((x, y)\) as:

\[\texttt{orientation} (x,y)= \arctan{\frac{d\texttt{mhi}/dy}{d\texttt{mhi}/dx}}\]

In fact, fastAtan2 and phase are used so that the computed angle is measured in degrees and covers the full range 0..360. Also, the mask is filled to indicate pixels where the computed angle is valid.

Note

• (Python) An example on how to perform a motion template technique can be found at opencv_source_code/samples/python2/motempl.py

calcOpticalFlowSF() [1/2]

void cv::optflow::calcOpticalFlowSF	(	InputArray	from,
		InputArray	to,
		OutputArray	flow,
		int	layers,
		int	averaging_block_size,
		int	max_flow
	)

Python:
	flow	=	cv.optflow.calcOpticalFlowSF(	from, to, layers, averaging_block_size, max_flow[, flow]	)
	flow	=	cv.optflow.calcOpticalFlowSF(	from, to, layers, averaging_block_size, max_flow, sigma_dist, sigma_color, postprocess_window, sigma_dist_fix, sigma_color_fix, occ_thr, upscale_averaging_radius, upscale_sigma_dist, upscale_sigma_color, speed_up_thr[, flow]	)

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

calcOpticalFlowSF() [2/2]

void cv::optflow::calcOpticalFlowSF	(	InputArray	from,
		InputArray	to,
		OutputArray	flow,
		int	layers,
		int	averaging_block_size,
		int	max_flow,
		double	sigma_dist,
		double	sigma_color,
		int	postprocess_window,
		double	sigma_dist_fix,
		double	sigma_color_fix,
		double	occ_thr,
		int	upscale_averaging_radius,
		double	upscale_sigma_dist,
		double	upscale_sigma_color,
		double	speed_up_thr
	)

Python:
	flow	=	cv.optflow.calcOpticalFlowSF(	from, to, layers, averaging_block_size, max_flow[, flow]	)
	flow	=	cv.optflow.calcOpticalFlowSF(	from, to, layers, averaging_block_size, max_flow, sigma_dist, sigma_color, postprocess_window, sigma_dist_fix, sigma_color_fix, occ_thr, upscale_averaging_radius, upscale_sigma_dist, upscale_sigma_color, speed_up_thr[, flow]	)

Calculate an optical flow using "SimpleFlow" algorithm.

Parameters

from	First 8-bit 3-channel image.
to	Second 8-bit 3-channel image of the same size as prev
flow	computed flow image that has the same size as prev and type CV_32FC2
layers	Number of layers
averaging_block_size	Size of block through which we sum up when calculate cost function for pixel
max_flow	maximal flow that we search at each level
sigma_dist	vector smooth spatial sigma parameter
sigma_color	vector smooth color sigma parameter
postprocess_window	window size for postprocess cross bilateral filter
sigma_dist_fix	spatial sigma for postprocess cross bilateralf filter
sigma_color_fix	color sigma for postprocess cross bilateral filter
occ_thr	threshold for detecting occlusions
upscale_averaging_radius	window size for bilateral upscale operation
upscale_sigma_dist	spatial sigma for bilateral upscale operation
upscale_sigma_color	color sigma for bilateral upscale operation
speed_up_thr	threshold to detect point with irregular flow - where flow should be recalculated after upscale

See [190] . And site of project - http://graphics.berkeley.edu/papers/Tao-SAN-2012-05/.

Note

• An example using the simpleFlow algorithm can be found at samples/simpleflow_demo.cpp

calcOpticalFlowSparseToDense()

void cv::optflow::calcOpticalFlowSparseToDense	(	InputArray	from,
		InputArray	to,
		OutputArray	flow,
		int	grid_step = 8,
		int	k = 128,
		float	sigma = 0.05f,
		bool	use_post_proc = true,
		float	fgs_lambda = 500.0f,
		float	fgs_sigma = 1.5f
	)

Python:
	flow	=	cv.optflow.calcOpticalFlowSparseToDense(	from, to[, flow[, grid_step[, k[, sigma[, use_post_proc[, fgs_lambda[, fgs_sigma]]]]]]]	)

Fast dense optical flow based on PyrLK sparse matches interpolation.

Parameters

from	first 8-bit 3-channel or 1-channel image.
to	second 8-bit 3-channel or 1-channel image of the same size as from
flow	computed flow image that has the same size as from and CV_32FC2 type
grid_step	stride used in sparse match computation. Lower values usually result in higher quality but slow down the algorithm.
k	number of nearest-neighbor matches considered, when fitting a locally affine model. Lower values can make the algorithm noticeably faster at the cost of some quality degradation.
sigma	parameter defining how fast the weights decrease in the locally-weighted affine fitting. Higher values can help preserve fine details, lower values can help to get rid of the noise in the output flow.
use_post_proc	defines whether the ximgproc::fastGlobalSmootherFilter() is used for post-processing after interpolation
fgs_lambda	see the respective parameter of the ximgproc::fastGlobalSmootherFilter()
fgs_sigma	see the respective parameter of the ximgproc::fastGlobalSmootherFilter()

createOptFlow_DeepFlow()

Ptr<DenseOpticalFlow> cv::optflow::createOptFlow_DeepFlow

(

)

Python:
	retval	=	cv.optflow.createOptFlow_DeepFlow(		)

DeepFlow optical flow algorithm implementation.

The class implements the DeepFlow optical flow algorithm described in [216] . See also http://lear.inrialpes.fr/src/deepmatching/ . Parameters - class fields - that may be modified after creating a class instance:

• member float alpha Smoothness assumption weight
• member float delta Color constancy assumption weight
• member float gamma Gradient constancy weight
• member float sigma Gaussian smoothing parameter
• member int minSize Minimal dimension of an image in the pyramid (next, smaller images in the pyramid are generated until one of the dimensions reaches this size)
• member float downscaleFactor Scaling factor in the image pyramid (must be < 1)
• member int fixedPointIterations How many iterations on each level of the pyramid
• member int sorIterations Iterations of Succesive Over-Relaxation (solver)
• member float omega Relaxation factor in SOR

createOptFlow_DualTVL1()

Ptr<DualTVL1OpticalFlow> cv::optflow::createOptFlow_DualTVL1

(

)

Python:
	retval	=	cv.optflow.createOptFlow_DualTVL1(		)

Creates instance of cv::DenseOpticalFlow.

createOptFlow_Farneback()

Ptr<DenseOpticalFlow> cv::optflow::createOptFlow_Farneback

(

)

Python:
	retval	=	cv.optflow.createOptFlow_Farneback(		)

Additional interface to the Farneback's algorithm - calcOpticalFlowFarneback()

createOptFlow_PCAFlow()

Ptr<DenseOpticalFlow> cv::optflow::createOptFlow_PCAFlow

(

)

Python:
	retval	=	cv.optflow.createOptFlow_PCAFlow(		)

Creates an instance of PCAFlow.

createOptFlow_SimpleFlow()

Ptr<DenseOpticalFlow> cv::optflow::createOptFlow_SimpleFlow

(

)

Python:
	retval	=	cv.optflow.createOptFlow_SimpleFlow(		)

Additional interface to the SimpleFlow algorithm - calcOpticalFlowSF()

createOptFlow_SparseToDense()

Ptr<DenseOpticalFlow> cv::optflow::createOptFlow_SparseToDense

(

)

Python:
	retval	=	cv.optflow.createOptFlow_SparseToDense(		)

Additional interface to the SparseToDenseFlow algorithm - calcOpticalFlowSparseToDense()

findCorrespondences()

template<int T>

void cv::optflow::GPCForest< T >::findCorrespondences	(	InputArray	imgFrom,
		InputArray	imgTo,
		std::vector< std::pair< Point2i, Point2i > > &	corr,
		const GPCMatchingParams	params = GPCMatchingParams()
	)		const

Find correspondences between two images.

Parameters

[in]	imgFrom	First image in a sequence.
[in]	imgTo	Second image in a sequence.
[out]	corr	Output vector with pairs of corresponding points.
[in]	params	Additional matching parameters for fine-tuning.

segmentMotion()

void cv::motempl::segmentMotion	(	InputArray	mhi,
		OutputArray	segmask,
		std::vector< Rect > &	boundingRects,
		double	timestamp,
		double	segThresh
	)

Python:
	segmask, boundingRects	=	cv.motempl.segmentMotion(	mhi, timestamp, segThresh[, segmask]	)

Splits a motion history image into a few parts corresponding to separate independent motions (for example, left hand, right hand).

Parameters

mhi	Motion history image.
segmask	Image where the found mask should be stored, single-channel, 32-bit floating-point.
boundingRects	Vector containing ROIs of motion connected components.
timestamp	Current time in milliseconds or other units.
segThresh	Segmentation threshold that is recommended to be equal to the interval between motion history "steps" or greater.

The function finds all of the motion segments and marks them in segmask with individual values (1,2,...). It also computes a vector with ROIs of motion connected components. After that the motion direction for every component can be calculated with calcGlobalOrientation using the extracted mask of the particular component.

updateMotionHistory()

void cv::motempl::updateMotionHistory	(	InputArray	silhouette,
		InputOutputArray	mhi,
		double	timestamp,
		double	duration
	)

Python:
	mhi	=	cv.motempl.updateMotionHistory(	silhouette, mhi, timestamp, duration	)

Updates the motion history image by a moving silhouette.

Parameters

silhouette	Silhouette mask that has non-zero pixels where the motion occurs.
mhi	Motion history image that is updated by the function (single-channel, 32-bit floating-point).
timestamp	Current time in milliseconds or other units.
duration	Maximal duration of the motion track in the same units as timestamp .

The function updates the motion history image as follows:

\[\texttt{mhi} (x,y)= \forkthree{\texttt{timestamp}}{if \(\texttt{silhouette}(x,y) \ne 0\)}{0}{if \(\texttt{silhouette}(x,y) = 0\) and \(\texttt{mhi} < (\texttt{timestamp} - \texttt{duration})\)}{\texttt{mhi}(x,y)}{otherwise}\]

That is, MHI pixels where the motion occurs are set to the current timestamp , while the pixels where the motion happened last time a long time ago are cleared.

The function, together with calcMotionGradient and calcGlobalOrientation , implements a motion templates technique described in [42] and [24] .